{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:19:14Z","timestamp":1791911954295,"version":"4.3.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012274","type":"print"},{"value":"9783030012281","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01228-1_23","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"379-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":259,"title":["Online Multi-Object Tracking with Dual Matching Attention Networks"],"prefix":"10.1007","author":[{"given":"Ji","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"23_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TPAMI.2017.2691769","volume":"40","author":"SH Bae","year":"2017","unstructured":"Bae, S.H., Yoon, K.J.: Confidence-based data association and discriminative deep appearance learning for robust online multi-object tracking. TPAMI 40, 595\u2013610 (2017)","journal-title":"TPAMI"},{"key":"23_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-319-48881-3_5","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Y Ban","year":"2016","unstructured":"Ban, Y., Ba, S., Alameda-Pineda, X., Horaud, R.: Tracking multiple persons based on a variational bayesian model. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 52\u201367. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_5"},{"key":"23_CR4","first-page":"1","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. JIVP 2008, 1 (2008)","journal-title":"JIVP"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Bochinski, E., Eiselein, V., Sikora, T.: High-speed tracking-by-detection without using image information. In: AVSS Workshop (2017)","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Bulo, S.R., Neuhold, G., Kontschieder, P.: Loss max-pooling for semantic image segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.749"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Sheng, H., Zhang, Y., Xiong, Z.: Enhancing detection model for multiple hypothesis tracking. In: CVPR Workshop (2017)","DOI":"10.1109\/CVPRW.2017.266"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Lawrence Zitnick, C.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Choi, W.: Near-online multi-target tracking with aggregated local flow descriptor. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.347"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Chu, Q., Ouyang, W., Li, H., Wang, X., Liu, B., Yu, N.: Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.518"},{"key":"23_CR11","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"23_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-319-46454-1_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Danelljan","year":"2016","unstructured":"Danelljan, M., Robinson, A., Shahbaz Khan, F., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 472\u2013488. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_29"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Dehghan, A., Tian, Y., Torr, P.H., Shah, M.: Target identity-aware network flow for online multiple target tracking. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298718"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Eiselein, V., Arp, D., P\u00e4tzold, M., Sikora, T.: Real-time multi-human tracking using a probability hypothesis density filter and multiple detectors. In: AVSS (2012)","DOI":"10.1109\/AVSS.2012.59"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: Cascade object detection with deformable part models. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539906"},{"issue":"9","key":"23_CR19","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9), 1627\u20131645 (2010)","journal-title":"TPAMI"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR21","unstructured":"Keuper, M., Tang, S., Zhongjie, Y., Andres, B., Brox, T., Schiele, B.: A multi-cut formulation for joint segmentation and tracking of multiple objects. arXiv preprint arXiv:1607.06317 (2016)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Kieritz, H., Becker, S., H\u00fcbner, W., Arens, M.: Online multi-person tracking using integral channel features. In: AVSS (2016)","DOI":"10.1109\/AVSS.2016.7738059"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Kim, C., Li, F., Ciptadi, A., Rehg, J.M.: Multiple hypothesis tracking revisited. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.533"},{"key":"23_CR24","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"23_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-319-16181-5_14","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"M Kristan","year":"2015","unstructured":"Kristan, M., et al.: The visual object tracking VOT2014 challenge results. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8926, pp. 191\u2013217. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16181-5_14"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Kutschbach, T., Bochinski, E., Eiselein, V., Sikora, T.: Sequential sensor fusion combining probability hypothesis density and kernelized correlation filters for multi-object tracking in video data. In: AVSS (2017)","DOI":"10.1109\/AVSS.2017.8078517"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9, L., Canton-Ferrer, C., Schindler, K.: Learning by tracking: Siamese CNN for robust target association. In: CVPR Workshop (2016)","DOI":"10.1109\/CVPRW.2016.59"},{"key":"23_CR28","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., Schindler, K.: MOTchallenge 2015: towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942 (2015)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Levinkov, E., et al.: Joint graph decomposition & node labeling: problem, algorithms, applications. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.206"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Li, W., Wang, X.: Locally aligned feature transforms across views. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.461"},{"key":"23_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-642-37331-2_3","volume-title":"Computer Vision \u2013 ACCV 2012","author":"W Li","year":"2013","unstructured":"Li, W., Zhao, R., Wang, X.: Human reidentification with transferred metric learning. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 31\u201344. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_3"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.27"},{"issue":"12","key":"23_CR33","first-page":"5630","volume":"24","author":"P Liang","year":"2015","unstructured":"Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. TIP 24(12), 5630\u20135644 (2015)","journal-title":"TIP"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"23_CR35","unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831 (2016)"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Milan, A., Rezatofighi, S.H., Dick, A.R., Reid, I.D., Schindler, K.: Online multi-target tracking using recurrent neural networks. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11194"},{"issue":"1","key":"23_CR37","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/TPAMI.2013.103","volume":"36","author":"A Milan","year":"2014","unstructured":"Milan, A., Roth, S., Schindler, K.: Continuous energy minimization for multitarget tracking. TPAMI 36(1), 58\u201372 (2014)","journal-title":"TPAMI"},{"key":"23_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-46448-0_27","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Mueller","year":"2016","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445\u2013461. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995604"},{"key":"23_CR40","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"23_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-48881-3_2","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Ristani","year":"2016","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_2"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Sadeghian, A., Alahi, A., Savarese, S.: Tracking the untrackable: learning to track multiple cues with long-term dependencies. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.41"},{"key":"23_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-319-48881-3_7","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"R Sanchez-Matilla","year":"2016","unstructured":"Sanchez-Matilla, R., Poiesi, F., Cavallaro, A.: Online multi-target tracking with strong and weak detections. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 84\u201399. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_7"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Son, J., Baek, M., Cho, M., Han, B.: Multi-object tracking with quadruplet convolutional neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.403"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Tang, S., Andres, B., Andriluka, M., Schiele, B.: Subgraph decomposition for multi-target tracking. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299138"},{"key":"23_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-319-48881-3_8","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"S Tang","year":"2016","unstructured":"Tang, S., Andres, B., Andriluka, M., Schiele, B.: Multi-person tracking by multicut and deep matching. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 100\u2013111. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_8"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Andres, B., Schiele, B.: Multiple people tracking by lifted multicut and person re-identification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.394"},{"key":"23_CR49","first-page":"1512","volume":"18","author":"J Van De Weijer","year":"2009","unstructured":"Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. TIP 18, 1512\u20131523 (2009)","journal-title":"TIP"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.683"},{"issue":"11","key":"23_CR51","doi-asserted-by":"publisher","first-page":"2312","DOI":"10.1109\/TPAMI.2015.2513406","volume":"38","author":"X Wang","year":"2016","unstructured":"Wang, X., T\u00fcretken, E., Fleuret, F., Fua, P.: Tracking interacting objects using intertwined flows. TPAMI 38(11), 2312\u20132326 (2016)","journal-title":"TPAMI"},{"issue":"9","key":"23_CR52","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Object tracking benchmark. TPAMI 37(9), 1834\u20131848 (2015)","journal-title":"TPAMI"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., Savarese, S.: Learning to track: online multi-object tracking by decision making. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.534"},{"key":"23_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"23_CR55","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Yang, F., Choi, W., Lin, Y.: Exploit all the layers: fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.234"},{"key":"23_CR57","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"23_CR58","unstructured":"Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01228-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:26:40Z","timestamp":1665016000000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}